Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    need to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мок
    1.10
     Ratch
    0.95
     maad
    0.92
    abba
    0.91
     Mitochond
    0.91
    ровку
    0.91
     Rama
    0.90
    abilă
    0.90
     renouvel
    0.90
    acks
    0.88
    POSITIVE LOGITS
     Cupid
    0.93
     cupid
    0.82
     BF
    0.81
     Jus
    0.78
     gau
    0.76
    (.
    0.75
     Franz
    0.74
     decimal
    0.73
     romant
    0.73
     Goddard
    0.73
    Act Density 0.436%

    No Known Activations